Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Non-English text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ஹ
    -0.07
    漋
    -0.07
    峛
    -0.07
     "-",
    -0.07
    嗍
    -0.06
    𝗕
    -0.06
    ibrary
    -0.06
    .logged
    -0.06
    eper
    -0.06
    icits
    -0.06
    POSITIVE LOGITS
     mar
    0.07
    Navigation
    0.07
    $r
    0.07
    eries
    0.07
    掀起
    0.07
    콰
    0.07
    现货
    0.07
    .lists
    0.06
     meat
    0.06
     victories
    0.06
    Act Density 0.012%

    No Known Activations